AutoSEE: An Artificial Intelligence Agent for Automated Solid Electrolyte Exploration

AutoSEE: агент искусственного интеллекта для автоматизированного исследования твердых электролитов
Chunpeng Yang, Qilong Wang, Feifei Luo, Deyuan Li, Zhenyi Lin
2026-04-02

GPT-4o research agentautomated solid electrolyte explorationhalide solid electrolytesionic conductivityunsupervised clustering
To address the challenge of complex chemical spaces in solid-state battery research, we develop a research agent for automated solid electrolyte exploration, AutoSEE, which enables efficient end-to-end research, autonomously revealing design principles for high-performance solid electrolytes. By leveraging GPT-4o as a central controller, AutoSEE orchestrates specialized tools such as literature screening, text mining, and machine learning to construct specialized data sets and distill principles. Taking halide solid electrolytes as an example, AutoSEE processes 226 relevant articles with an average precision of 93.4% within 5 min and employs unsupervised clustering to autonomously distill a critical design principle that halide solid electrolytes featuring high charge density favor an amorphous phase and high ionic conductivity. Guided by this principle, we found an unexplored electrolyte LiTaB 0.32 O 0.98 Cl 5, which possesses a high ionic conductivity (7.82 mS cm –1 ), experimentally validating the agent-distilled rule. AutoSEE showcases a paradigm shift from simple data retrieval to agentic knowledge exploration.
1
AutoSEE is an end-to-end AI research agent that combines GPT-4o with literature screening, text mining, and machine learning for automated solid-electrolyte exploration.
2
AutoSEE screened 226 halide solid-electrolyte articles with an average precision of 93.4% within five minutes.
3
Experimental validation of the discovered electrolyte supports the agent-derived design rule and demonstrates a shift from data retrieval toward autonomous knowledge exploration.
4
Guided by the extracted principle, the study discovered unexplored LiTaB0.32O0.98Cl5 with ionic conductivity of 7.82 mS cm−1.
5
Unsupervised clustering identified a design principle linking high charge density in halide solid electrolytes with amorphous phases and high ionic conductivity.

halide solid electrolytes

the relationship between charge density, amorphous-phase formation, and ionic conductivity, including the discovery of high-performance compositions

Publication Details
Publication Date
2026-04-02
Journal
Publisher
ISSN
Cited by
4
Access Type
Author Information
Authors
Chunpeng Yang
Qilong Wang
Feifei Luo
Deyuan Li
Zhenyi Lin
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%